检索结果-内蒙古大学图书馆

32nd Italian Symposium on Advanced Database Systems, SEBD 2024

作者： Balzotti, Lorenzo Franciosa, Paolo G. Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Department of Statistical Science Sapienza University of Rome p.le Aldo Moro 5 Rome00185 Italy

In the real world, planar networks commonly model utility distribution networks such as gas pipelines, water distribution, city's electric grid, and transportation networks like railways and highways. Evaluating the vulnerability of these networks is crucial on several point of view: in a military context in order to prevent terrorist attack, or for maintenance to prevent wear and tear or natural disasters from inflicting extremely severe damage. This work aims to evaluate the vulnerability of undirected planar network studying the decrease of maximum st-flow when an edge or a vertex is removed, that is, we propose algorithms for computing the max flow vitality of edges and vertices. Our algorithms are applied to real world scenarios, and we prove that high vitality values are well approximated in time close to the time currently required to compute st-max flow O(n log log n). All our algorithms work in O(n) space. © 2024 Copyright for this paper by its authors.

关键词： Natural gas pipelines

来源：评论

学校读者我要写书评

暂无评论

Automatic Liver Segmentation from Multiphase CT Using Modified SegNet and ASPP Module

引用

SN computer science 2024年第4期5卷 377页

作者： Nayantara, P. Vaidehi Kamath, Surekha Kadavigere, Rajagopal Manjunath, Kanabagatte Nanjundappa Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Radiodiagnosis and Imaging Kasturba Medical College Manipal Academy of Higher Education Karnataka Manipal 576104 India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India

Liver cancer is one of the dominant causes of cancer death worldwide. Computed Tomography (CT) is the commonly used imaging modality for diagnosing it. computer-based liver cancer diagnosis systems can assist radiologists in image interpretation and improve diagnosis speed and accuracy. Since liver segmentation is crucial to such systems, researchers are relentlessly pursuing various segmentation approaches. A clinically viable computer-aided system requires examining multiphase CT images. However, most of the research focuses only on the portal venous phase. In this work, we developed an automatic and efficient Deep Learning (DL) method using SegNet, atrous spatial pyramid pooling module and leaky ReLU layers for liver segmentation from quadriphasic abdominal CT volumes. The proposed method was validated on two datasets, an internal institutional dataset consisting of multiphase CT and a public dataset of portal venous phase CT volumes. The Dice Coefficients (DC) obtained were greater than 96% for the latter dataset and the portal venous phase of the former. For arterial, delayed and plain CT phases of the former dataset, the DC achieved were 94.61%, 95.01% and 93.23%, respectively. Experiments showed that our model performed better than the other state-of-the-art DL models. Ablation studies have revealed that the proposed model leverages the strengths of all the three components that make it up. The promising performance of the proposed method suggests that it is appropriate for incorporation in hepatic cancer diagnosis systems. © The Author(s) 2024.

关键词： Atrous spatial pyramid pooling Computed tomography computer-aided diagnosis Liver cancer Liver segmentation SegNet

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Reliability of Supervised Compression for Split Computing

Evaluating the Reliability of Supervised Compression for Spl...

引用

VLSI Test Symposium

作者： Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Marco Levorato Matteo Sonza Reorda Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Turin Italy Computer Science Department University of California Irvine US

ISBN: (数字)9798350363784

ISBN: (纸本)9798350363791

Recent advances in Internet-of-things (IoT) and 5G infrastructures promote new computational paradigms such as Split Computing (SC) for deploying Deep Neural Networks (DNNs) on mobile applications. In SC, DNNs are partitioned into head and tail sub-models that are executed on the mobile device and cloud/edge servers, respectively. Modern SC models resort to head compression techniques to balance energy consumption, transmission data, and model size while preserving the outstanding accuracy of large state-of-the-art DNNs. These features make SC DNNs suitable for mobile applications, including safety-critical systems (e.g., self-driving vehicles, autonomous robots, and healthcare equipment), where reliability is a paramount factor mandated by strict safety standards. Despite there are many studies available about the reliability of DNNs, the SC models are still unexplored, especially when hardware faults threaten the operation of a mobile device. In this work, we present for the first time $i)$ an application-level fault injection strategy for modeling hardware faults on mobile GPUs executing SC DNNs and ii) an evaluation of the resilience of supervised compression methods utilized by SC systems. The preliminary results gathered on some representative benchmark networks and configurations show the feasibility and effectiveness of the approach. They also demonstrate that aggressive compression strategies lead to high accuracy degradation $(\approx$ 40%), increasing the overall vulnerability of the DNN and the system.

关键词： Computational modeling Artificial neural networks Tail Very large scale integration Mobile handsets Hardware Data models

来源：评论

学校读者我要写书评

暂无评论

Reactive Synthesis for Expected Impacts

arXiv

引用

arXiv 2024年

作者： Chini, Emanuele Sala, Pietro Simonetti, Andrea Zare, Omid Department of Computer Control and Management Engineering University La Sapienza Rome Italy Department of Computer Science University of Verona Verona Italy

As business processes become increasingly complex, effectively modeling decision points, their likelihood, and resource consumption is crucial for optimizing operations. To address this challenge, this paper introduces a formal extension of the Business Process Model and Notation (BPMN) that incorporates choices, probabilities, and impacts, referred to as BPMN+CPI. This extension is motivated by the growing emphasis on precise control within business process management, where carefully selecting decision pathways in repeated instances is crucial for conforming to certain standards of multiple resource consumption and environmental impacts. In this context we deal with the problem of synthesizing a strategy (if any) that guarantees that the expected impacts on repeated execution of the input process are below a given threshold. We show that this problem belongs to PSPACE complexity class;moreover we provide an effective procedure for computing a strategy (if present). © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optimization of Electric Vehicle Charging for Sustainable Power Grids using Sine Hunter-Prey Optimization with GRUs 3

Dynamic Optimization of Electric Vehicle Charging for Sustai...

引用

3rd IEEE International Conference on Electrical Power and Energy Systems, ICEPES 2024

作者： Syed, Mohd Khizar Chandra Behera, Prakash Josephson, P Joel Khan, Shamim Ahmad Kholmukhamedov, Timur Ponni Valavan, M. Kohinoor college Department of Physics Maharashtra India St. Claret College Department of Science Bangalore India Malla Reddy Engineering College Department of ECE Telangana Medchal Malkajgiri India Glocal School of Science & Technology Glocal University Uttar Pradesh India Turin Polytechnic University Automatic Control and Computer Engineering Department Tashkent Uzbekistan K.Ramakrishnan College of Engineering Department of AI & DS Tamil Nadu Trichy India

ISBN: (纸本)9798350390728

The integration of electric vehicles (EVs) into power grids presents a significant challenge for sustainability due to their dynamic charging demands and the need to accommodate renewable energy sources. Existing optimization methods often fail to adequately address the complexity of this problem. In this study, propose a novel approach that combines Sine Hunter-Prey Optimization (SHPO) with Gated Recurrent Units (GRUs) to dynamically optimize EV charging for sustainable power grid operation. Traditional optimization methods struggle to capture the nonlinear and time-varying nature of EV charging demands and renewable energy availability. To overcome this limitation, SHPO's ability to efficiently explore complex solution spaces and GRUs' capability to model temporal dependencies in sequential data. This proposed method optimizes EV charging schedules by considering grid stability, renewable energy utilization, and cost minimization. Validating the approach using historical data on EV charging patterns, renewable energy generation, and grid conditions. Performance metrics include grid stability indices, renewable energy integration rates, and cost savings compared to baseline strategies. Experimental results demonstrate that the method outperforms traditional optimization techniques, leading to more sustainable and resilient power grid operation with 92% stability. Overall, this study contributes to advancing the modern methods in dynamic optimization of EV charging, paving the way for more sustainable transportation and energy systems. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Effective Application-level Error Modeling of Permanent Faults on AI Accelerators

Effective Application-level Error Modeling of Permanent Faul...

引用

IEEE Symposium on On-Line Testing (IOLTS)

作者： Francesco Pessia Juan-David Guerrero-Balaguera Robert Limas Sierra Josie E. Rodriguez Condia Marco Levorato Matteo Sonza Reorda Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Turin Italy Computer Science Department University of California Irvine US

ISBN: (数字)9798350370553

ISBN: (纸本)9798350370560

The deployment of Machine Learning (ML) applications extensively leverages Matrix Multiplication (MM) operations on modern and advanced accelerators, like Graphic Processing Units (GPUs), which employ Tensor Core Units (TCUs) to optimize MM’s execution efficiently. However, reliability concerns arise in devices with cutting-edge semiconductor technologies (7 nm or less), as faults can compromise some structures (e.g., TCUs) during their operation. In safety-critical applications, this can lead to wrong DNN outcomes and cause unpredictable and unacceptable actions. Thus, the impact evaluation of such faults is crucial to ensure that TCUs and GPUs meet the safety standard requirements (e.g., ISO26262). Currently, the reliability assessment of complex applications concerning hardware faults involves fault injection (FI) campaigns. Unfortunately, low-level FI campaigns might be computationally prohibitive for GPUs when these execute massive applications like DNNs. In this work, we propose an error modeling approach to accurately describe corruptions from permanent faults on TCUs, during the operation of MMs. This approach enables realistic reliability evaluations of computationally expensive MM-based workloads, resulting in a huge acceleration (up to 225X) compared with hardware-level FIs. Our experimental results show a very good accuracy (up to $93 \%$ correlation between our error modeling approach and FI campaigns conducted on TCUs).

关键词： Tensors Computational modeling Machine learning Reliability engineering Safety System analysis and design Standards

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Reliability of Split Computing Deep Neural Networks

Enhancing the Reliability of Split Computing Deep Neural Net...

引用

IEEE Symposium on On-Line Testing (IOLTS)

作者： Giuseppe Esposito Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Marco Levorato Matteo Sonza Reorda Politecnico di Torino - Department of Control and Computer Engineering (DAUIN) Turin Italy Computer Science Department University of California Irvine US

ISBN: (数字)9798350370553

ISBN: (纸本)9798350370560

Artificial intelligence is becoming increasingly popular for IoT applications in safety-critical fields (e.g., autonomous systems and biomedical, robots). Unfortunately, the inference’s workload process alone increases as the model size grows. To meet the computational power limitations of mobile devices running IoT applications, modern services sometimes resort to the Split Computing paradigm. Split Computing divides the inference process of a Neural Network into Head and Tail for their execution in a mobile device and a server, respectively, which also allows the reduction of the overall IoT device’s computational cost. Nonetheless, Split Computing can be used in safety-critical fields where reliability is crucial, especially when mobile devices have computational and cost restrictions. This paper introduces hardening techniques acting on the software to mitigate the effects of hardware faults on Split Computing models. The proposed hardening techniques consist of i) a bounded activation function whose thresholds are refined by training, and ii) a per-channel bounding of the bottleneck quantization of the split points. To quantitatively assess their effectiveness, we resorted to two different split configurations of a model for image classification. In addition, we considered a Split Computing model for object detection. Our findings indicate that the proposed approaches effectively reduces fault effects by $\mathbf{3. 5 \%}$ for image classifiers and $5.73 \%$ for object detectors when compared with other hardening approaches for general DNNs.

关键词： Training Quantization (signal) Head Computational modeling Object detection Artificial neural networks Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

Fuzzy control design for time-delay systems under adaptive event-triggered mechanism

引用

Neural Computing and Applications 2024年第9期36卷 4727-4739页

作者： Du, Zhenbin Qu, Zifang Kao, Yonggui Wu, Zhaojing School of Computer and Control Engineering Yantai University Shandong Yantai264005 China School of Mathematics and Information Science Shandong Technology and Business University Shandong Yantai264005 China Department of Mathematics Harbin Institute of Technology Weihai264209 China School of Mathematics and Information Sciences Yantai University Shandong Yantai264005 China

This manuscript studies the fuzzy H∞ control design problem for nonlinear time-varying delay systems in fuzzy form via adaptive event-triggered mechanism. The fuzzy model and an adaptive event-triggered controller are connected in closed-loop form. A looped-functional is established to conduct stability analysis, and the main feature of this functional can fully reflect the sampling feature of control systems. Thus, the achieved results are less conservative. The Wringter inequality is also used to further relax stability analysis. Finally, sufficient conditions are achieved for the existence of event-triggered fuzzy controller, and the resulting closed-loop system reaches an H∞ control performance. Two examples verify the efficiency of the presented control strategy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Special Session: Software-Based Self-Test Generation for RISC-V – Stuck-At Generation, Functional Cell-Aware Untestability, and FPGA Demonstration –

Special Session: Software-Based Self-Test Generation for RIS...

引用

IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems

作者： Tobias Faller Nikolaos I. Deligiannis Riccardo Cantoro Matteo Sonza Reorda Bernd Becker Department of Computer Science University of Freiburg Freiburg Germany Department of Control and Computer Engineering (DAUIN) Politecnico di Torino Turin Italy

ISBN: (数字)9798350366884

ISBN: (纸本)9798350366891

Software-Based Self-Tests (SBST) allow at-speed, native online-testing of processors by running software programs on the processor core, requiring no Design for Testability (DfT) infrastructure. Traditionally, the generation of such SBST programs requires time-consuming manual labor in combination with in-depth knowledge of the processor's architecture to target hard-to-test faults. In contrast, encoding the SBST generation task as a Bounded Model Checking (BMC) problem allows using sophisticated, state-of-the-art BMC solvers to automatically generate an SBST for a given fault model and, moreover, prove the untestability of certain faults. During generation, a constraint specification Validity Checker Module (VCM) ensures correct, functional SBST behavior. The operating conditions in the field and the processor and system-specific constraints are included in this specification, too, in a highly configurable form. In this paper, we present an intermediate VCM interface to generalize the functional constraint specification on RISC-V processors and apply it to two in-field test-related areas. First, we perform SBST generation for detecting permanent hardware faults (stuck-at) in the ALU and the register file of multiple RISC-V processors. Second, we perform functional untestability analysis for the cell-aware fault model on the same processors. Finally, we synthesize the largest processor core on an FPGA with user-controlled fault injection to demonstrate the subsequent detection via the generated stuck-at SBST to a non-technical audience.

关键词： Fault diagnosis Program processors Runtime Built-in self-test Very large scale integration Software Registers Test pattern generators Field programmable gate arrays Nanotechnology

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning Models for Predicting Students' Performance in Mathematics: A K-Fold Approach

Application of Machine Learning Models for Predicting Studen...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ale, Felix Ikpaya, Ikpaya D. Danyan, Ilesanmi Opateye, Goodness O. Onwodi, Gregory Agboola, Olufemi O. National Space Research & Development Agency Department of Engineering & Space Systems Abuja Nigeria National Space Research & Development Agency Ground Station & Mission Control Abuja Nigeria Achievers University Department of Mechanical & Mechatronics Engineering Owo Nigeria National Open University of Nigeria Department of Computer Science Abuja Nigeria

ISBN: (纸本)9798350358155

Mathematics plays a pivotal role in science, technology and engineering. It is one of the compulsory subjects to gain admission into a higher institution in Nigeria. Considering its importance, students' performance has been a significant concern for most educators, government, parents and guardians. This study aims to predict students' performance in mathematics using the K-fold approach to support effective decision-making and policy implementation on mathematics. The primary dataset was collected from 192 senior secondary schools, and one mathematics student was randomly selected from five Senior Secondary Schools in Bwari Area Council, Abuja, and used as a sample. Students' Mathematics Achievement Test (SMAT) was used as the instrument to collect data. The data was processed and modelled using the Python Programming language. Thus, five machine learning models were trained and evaluated to overcome overfitting using four-, five - -, and six-fold K-Fold cross-validation techniques. Five folds performed best for all the models except for the Support Vector Regressor, which performed best with six folds. The evaluation of the models showed that the Light Gradient Boosting Model outperformed others with a Mean Absolute Error of 12.642 and a Root Mean Square Error of 15.894. The models were significantly influenced by the students' personal study time, friends' assistance, and the parents' educational background. It is therefore recommended that academic researchers, educational authorities in Nigeria, and relevant stakeholders use and improve on this model to predict the students' scores and assist them in achieving great performance in mathematics. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：